TensorFlow学习之深度学习破解验证码

---

在同学的演讲中了解到了TensorFlow，上网查TensorFlow最初是由Google大脑小组的工程师开发出来的，用于的是机器学习和深度神经网络方面的研究。现在已经完全开源，可以拿这个用于语音识别和图像识别等机器学习。

于是找了个例子练习下，以前做验证码破解都是直接使用别人的库，效率低识别差，好的需要自己写算法或者是购买第三方的，比较麻烦。使用了这个机器学习的验证码识别，感觉这个cnn的识别效果还是不错的。下面具体来看下怎么实现深度学习验证码破解。

---

前言

验证码主要是用于防刷，传统的验证码算法是通过把验证码分割为单个的字符，然后逐个的识别，如果复杂的验证码字母之间相互重叠，那么就无法识别了，这里采用的cnn可以对验证码整体进行有效的识别。
学习的要点：

1、captcha库生成验证码
2、如何将验证码识别问题转化为分类问题
3、可以训练自己的验证码识别模型

---

生成验证码训练数据

所有的训练模型，数据才是关键，这里采用的captcha库生成验证码，captcha可以生成语音和图片验证码，验证码是由数字、大小写字母（也可以自定义特殊字符），长度为4，共有62^4种组合。

本文的系统为centos，首先安装captcha库：

sudo pip install captcha

验证码生成器：

采用python中生成器方式来生成训练数据，这样的好处是不需要提前生成大量的数据，而是在训练的过程中生成数据，可以无限的生成数据。

创建一个源文件：

vim generate_captcha.py

参考代码：

#!/usr/bin/python
# -*- coding: utf-8 -*
from captcha.image import ImageCaptcha
from PIL import Image
import numpy as np
import random
import string
class generateCaptcha():
    def __init__(self,
                 width = 160,#验证码图片的宽
                 height = 60,#验证码图片的高
                 char_num = 4,#验证码字符个数
                 characters = string.digits + string.ascii_uppercase + string.ascii_lowercase):#验证码组成，数字+大写字母+小写字母
        self.width = width
        self.height = height
        self.char_num = char_num
        self.characters = characters
        self.classes = len(characters)
    def gen_captcha(self,batch_size = 50):
        X = np.zeros([batch_size,self.height,self.width,1])
        img = np.zeros((self.height,self.width),dtype=np.uint8)
        Y = np.zeros([batch_size,self.char_num,self.classes])
        image = ImageCaptcha(width = self.width,height = self.height)
        while True:
            for i in range(batch_size):
                captcha_str = ''.join(random.sample(self.characters,self.char_num))
                img = image.generate_image(captcha_str).convert('L')
                img = np.array(img.getdata())
                X[i] = np.reshape(img,[self.height,self.width,1])/255.0
                for j,ch in enumerate(captcha_str):
                    Y[i,j,self.characters.find(ch)] = 1
            Y = np.reshape(Y,(batch_size,self.char_num*self.classes))
            yield X,Y
    def decode_captcha(self,y):
        y = np.reshape(y,(len(y),self.char_num,self.classes))
        return ''.join(self.characters[x] for x in np.argmax(y,axis = 2)[0,:])
    def get_parameter(self):
        return self.width,self.height,self.char_num,self.characters,self.classes
    def gen_test_captcha(self):
        image = ImageCaptcha(width = self.width,height = self.height)
        captcha_str = ''.join(random.sample(self.characters,self.char_num))
        img = image.generate_image(captcha_str)
        img.save(captcha_str + '.jpg')

然后执行源文件：

python
>>>import generate_captcha
>>>g = generate_captcha.generateCaptcha()
>>>g.gen_test_captcha()

然后可以在当前目录下查看生成的验证码

---

验证码识别模型

将验证码识别问题转化为分类问题，总共62^4中类型，采用4个one-hot编码分别表示4中字符取值

cnn验证码识别模型

3 层隐藏层、2 层全连接层，对每层都进行 dropout。
input——>conv——>pool——>dropout——>conv——>pool——>dropout——>conv——>pool——>dropout——>fully connected layer——>dropout——>fully connected layer——>output

创建源文件captcha_model.py，参考代码如下：

#!/usr/bin/python
# -*- coding: utf-8 -*
import tensorflow as tf
import math
class captchaModel():
    def __init__(self,
                 width = 160,
                 height = 60,
                 char_num = 4,
                 classes = 62):
        self.width = width
        self.height = height
        self.char_num = char_num
        self.classes = classes
    def conv2d(self,x, W):
        return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
    def max_pool_2x2(self,x):
        return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                              strides=[1, 2, 2, 1], padding='SAME')
    def weight_variable(self,shape):
        initial = tf.truncated_normal(shape, stddev=0.1)
        return tf.Variable(initial)
    def bias_variable(self,shape):
        initial = tf.constant(0.1, shape=shape)
        return tf.Variable(initial)
    def create_model(self,x_images,keep_prob):
        #first layer
        w_conv1 = self.weight_variable([5, 5, 1, 32])
        b_conv1 = self.bias_variable([32])
        h_conv1 = tf.nn.relu(tf.nn.bias_add(self.conv2d(x_images, w_conv1), b_conv1))
        h_pool1 = self.max_pool_2x2(h_conv1)
        h_dropout1 = tf.nn.dropout(h_pool1,keep_prob)
        conv_width = math.ceil(self.width/2)
        conv_height = math.ceil(self.height/2)
        #second layer
        w_conv2 = self.weight_variable([5, 5, 32, 64])
        b_conv2 = self.bias_variable([64])
        h_conv2 = tf.nn.relu(tf.nn.bias_add(self.conv2d(h_dropout1, w_conv2), b_conv2))
        h_pool2 = self.max_pool_2x2(h_conv2)
        h_dropout2 = tf.nn.dropout(h_pool2,keep_prob)
        conv_width = math.ceil(conv_width/2)
        conv_height = math.ceil(conv_height/2)
        #third layer
        w_conv3 = self.weight_variable([5, 5, 64, 64])
        b_conv3 = self.bias_variable([64])
        h_conv3 = tf.nn.relu(tf.nn.bias_add(self.conv2d(h_dropout2, w_conv3), b_conv3))
        h_pool3 = self.max_pool_2x2(h_conv3)
        h_dropout3 = tf.nn.dropout(h_pool3,keep_prob)
        conv_width = math.ceil(conv_width/2)
        conv_height = math.ceil(conv_height/2)
        #first fully layer
        conv_width = int(conv_width)
        conv_height = int(conv_height)
        w_fc1 = self.weight_variable([64*conv_width*conv_height,1024])
        b_fc1 = self.bias_variable([1024])
        h_dropout3_flat = tf.reshape(h_dropout3,[-1,64*conv_width*conv_height])
        h_fc1 = tf.nn.relu(tf.nn.bias_add(tf.matmul(h_dropout3_flat, w_fc1), b_fc1))
        h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
        #second fully layer
        w_fc2 = self.weight_variable([1024,self.char_num*self.classes])
        b_fc2 = self.bias_variable([self.char_num*self.classes])
        y_conv = tf.add(tf.matmul(h_fc1_drop, w_fc2), b_fc2)
        return y_conv

训练cnn验证码识别模型：

这里采用了64个训练样本，每100次循环采用100个测试样本检查识别准确度，当准确度大于99%时，训练结束。

这里测试的话，可以将代码中的 if acc > 0.99 的准确度降低来减少训练的时间。

---

下面是一个已经训练好的训练集，可以下载下来看看最终的验证效果：

首先通过命令下载到本地：

wget http://tensorflow-1253902462.cosgz.myqcloud.com/captcha/capcha_model.zip
unzip capcha_model.zip

在当前目录下创建文件train_captcha.py，内容参考下面代码：

#!/usr/bin/python
import tensorflow as tf
import numpy as np
import string
import generate_captcha
import captcha_model
if __name__ == '__main__':
    captcha = generate_captcha.generateCaptcha()
    width,height,char_num,characters,classes = captcha.get_parameter()
    x = tf.placeholder(tf.float32, [None, height,width,1])
    y_ = tf.placeholder(tf.float32, [None, char_num*classes])
    keep_prob = tf.placeholder(tf.float32)
    model = captcha_model.captchaModel(width,height,char_num,classes)
    y_conv = model.create_model(x,keep_prob)
    cross_entropy = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=y_,logits=y_conv))
    train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
    predict = tf.reshape(y_conv, [-1,char_num, classes])
    real = tf.reshape(y_,[-1,char_num, classes])
    correct_prediction = tf.equal(tf.argmax(predict,2), tf.argmax(real,2))
    correct_prediction = tf.cast(correct_prediction, tf.float32)
    accuracy = tf.reduce_mean(correct_prediction)
    saver = tf.train.Saver()
    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        step = 0
        while True:
            batch_x,batch_y = next(captcha.gen_captcha(64))
            _,loss = sess.run([train_step,cross_entropy],feed_dict={x: batch_x, y_: batch_y, keep_prob: 0.75})
            print ('step:%d,loss:%f' % (step,loss))
            if step % 100 == 0:
                batch_x_test,batch_y_test = next(captcha.gen_captcha(100))
                acc = sess.run(accuracy, feed_dict={x: batch_x_test, y_: batch_y_test, keep_prob: 1.})
                print ('###############################################step:%d,accuracy:%f' % (step,acc))
                if acc > 0.99:
                    saver.save(sess,"capcha_model.ckpt")
                    break
            step += 1

测试识别模型：

创建源文件predict_captcha.py，参考代码如下：

#!/usr/bin/python
from PIL import Image, ImageFilter
import tensorflow as tf
import numpy as np
import string
import sys
import generate_captcha
import captcha_model
if __name__ == '__main__':
    captcha = generate_captcha.generateCaptcha()
    width,height,char_num,characters,classes = captcha.get_parameter()
    gray_image = Image.open(sys.argv[1]).convert('L')
    img = np.array(gray_image.getdata())
    test_x = np.reshape(img,[height,width,1])/255.0
    x = tf.placeholder(tf.float32, [None, height,width,1])
    keep_prob = tf.placeholder(tf.float32)
    model = captcha_model.captchaModel(width,height,char_num,classes)
    y_conv = model.create_model(x,keep_prob)
    predict = tf.argmax(tf.reshape(y_conv, [-1,char_num, classes]),2)
    init_op = tf.global_variables_initializer()
    saver = tf.train.Saver()
    gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.95)
    with tf.Session(config=tf.ConfigProto(log_device_placement=False,gpu_options=gpu_options)) as sess:
        sess.run(init_op)
        saver.restore(sess, "capcha_model.ckpt")
        pre_list =  sess.run(predict,feed_dict={x: [test_x], keep_prob: 1})
        for i in pre_list:
            s = ''
            for j in i:
                s += characters[j]
            print s

然后执行源文件，python predict_captcha.py Kz2J.jpg

执行结果：Kz2J

---

在训练时间足够长的情况下，你可以采用验证码生成器生成测试数据，cnn 训练出来的验证码识别模型还是很强大的，大小写的 z 都可以区分，甚至有时候人都无法区分，该模型也可以正确的识别。这个验证码识别还是可以破解大部分简单的验证码的，但是如果碰到中文的，那就需要一个集群来进行训练了。机器学习是非常强大的，可以说是大数据和人工智能的桥接处，以后多多了解。

腾讯云的TensorFlowAPI体验实验：https://cloud.tencent.com/developer/labs/lab/10187
TensorFlow中文社区文档：http://www.tensorfly.cn/tfdoc/get_started/introduction.html